Please use this identifier to cite or link to this item:
DC FieldValueLanguage
dc.contributor.authorFredouille , Corinneen_US
dc.contributor.authorMariethoz, Jen_US
dc.contributor.authorJaboulet , Cen_US
dc.contributor.authorMokbel, Chaficen_US
dc.description.abstractClassical adaptation approaches are generally used for speaker or environment adaptation of speech recognition systems. In this paper, we use such techniques for the incremental training of client models in a speaker verification system. The initial model is trained on a very limited amount of data and then progressively updated with access data, using a segmental-EM procedure. In supervised mode (i.e. when access utterances are certified), the incremental approach yields equivalent performance to the batch one. We also investigate on the impact of various scenarios of impostor attacks during the incremental enrollment phase. All results are obtained with the Picassoft platform-the state-of-the-art speaker verification system developed in the PICASSO project.en_US
dc.format.extent4 p.en_US
dc.subjectBayesian methodsen_US
dc.subjectHidden Markov modelsen_US
dc.subjectContext modelingen_US
dc.subjectSpeech recognitionen_US
dc.subjectSpeaker recognitionen_US
dc.subjectCovariance matrixen_US
dc.subjectViterbi algorithmen_US
dc.titleBehavior of a Bayesian adaptation method for incremental enrollment in speaker verificationen_US
dc.typeConference Paperen_US
dc.relation.conferenceInternational Conference on Acoustics, Speech, and Signal Processing (5-9 June 2000 : Istanbul, Turkey,)en_US
dc.contributor.affiliationDepartment of Electrical Engineeringen_US
dc.relation.ispartoftext2000 IEEE International Conference on Acoustics, Speech, and Signal Processing.en_US
dc.provenance.recordsourceOliben_US of Engineering-
Appears in Collections:Department of Electrical Engineering
Show simple item record

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.